Omni-Geo couples neural and symbolic reasoning in a unified typed geometry state, reaching 90.8% macro average across three geometry benchmarks and solving 21/30 IMO-AG-30 problems
The work formulates dense neural–symbolic coupling, in which neural proposals and symbolic execution share one typed geometry state and communicate through executable actions at every search step, instantiated as Omni-Geo, a single solver spanning plane, analytic (including conics), and solid geometry; with Claude Sonnet 4.6 it reaches 94.2%, 88.5%, and 89.8% on FormalGeo7K, Conic10K, and SolidFGeo (90.8% macro average) and solves 21/30 IMO-AG-30 problems.